Skip to yearly menu bar
Skip to main content
Main Navigation
AISTATS
Help/FAQ
Contact AISTATS
Code of Conduct
Create Profile
Privacy Policy
My Stuff
Login
Select Year: (2024)
2024
2023
2022
2021
Getting Started
Schedule
Invited Talks
Papers
ToT Awards
Sponsors
Organizers
Help
Code Of Conduct
Bookmarking/Agenda
Browse
Visualization
mini
compact
topic
detail
Showing papers for
.
×
×
title
author
topic
session
shuffle
by
serendipity
bookmarked first
visited first
not visited first
bookmarked but not visited
Enable Javascript in your browser to see the papers page.
MMD-based Variable Importance for Distributional Random Forest
Hidden yet quantifiable: A lower bound for confounding strength using randomized trials
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
DHMConv: Directed Hypergraph Momentum Convolution Framework
Directed Hypergraph Representation Learning for Link Prediction
TransFusion: Covariate-Shift Robust Transfer Learning for High-Dimensional Regression
Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process
Timing as an Action: Learning When to Observe and Act
SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits
Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation
Self-Supervised Quantization-Aware Knowledge Distillation
Revisiting the Noise Model of Stochastic Gradient Descent
Fairness in Submodular Maximization over a Matroid Constraint
On cyclical MCMC sampling
Benefits of Non-Linear Scale Parameterizations in Black Box Variational Inference through Smoothness Results and Gradient Variance Bounds
The AL$\ell_0$CORE Tensor Decomposition for Sparse Count Data
Strategic Usage in a Multi-Learner Setting
Importance Matching Lemma for Lossy Compression with Side Information
Spectrum Extraction and Clipping for Implicitly Linear Layers
Fitting ARMA Time Series Models without Identification: A Proximal Approach
Imposing Fairness Constraints in Synthetic Data Generation
DiffRed: Dimensionality reduction guided by stable rank
Tight Verification of Probabilistic Robustness in Bayesian Neural Networks
Parameter-Agnostic Optimization under Relaxed Smoothness
General Tail Bounds for Non-Smooth Stochastic Mirror Descent
Scalable Meta-Learning with Gaussian Processes
Multi-Domain Causal Representation Learning via Weak Distributional Invariances
Training a Tucker Model With Shared Factors: a Riemannian Optimization Approach
Communication-Efficient Federated Learning With Data and Client Heterogeneity
Shape Arithmetic Expressions: Advancing Scientific Discovery Beyond Closed-Form Equations
Pathwise Explanation of ReLU Neural Networks
Data-Driven Online Model Selection With Regret Guarantees
Generative Flow Networks as Entropy-Regularized RL
Attention-based Multi-instance Mixed Models
Non-Neighbors Also Matter to Kriging: A New Contrastive-Prototypical Learning
Sample-efficient neural likelihood-free Bayesian inference of implicit HMMs
Towards Practical Non-Adversarial Distribution Matching
P-tensors: a General Framework for Higher Order Message Passing in Subgraph Neural Networks
Learning the Pareto Set Under Incomplete Preferences: Pure Exploration in Vector Bandits
From Coupled Oscillators to Graph Neural Networks: Reducing Over-smoothing via a Kuramoto Model-based Approach
On the estimation of persistence intensity functions and linear representations of persistence diagrams
Data Driven Threshold and Potential Initialization for Spiking Neural Networks
On The Temporal Domain of Differential Equation Inspired Graph Neural Networks
Prior-dependent analysis of posterior sampling reinforcement learning with function approximation
Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles
Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods
Near-Optimal Convex Simple Bilevel Optimization with a Bisection Method
On the Expected Size of Conformal Prediction Sets
Electronic Medical Records Assisted Digital Clinical Trial Design
Discriminant Distance-Aware Representation on Deterministic Uncertainty Quantification Methods
Efficient Data Valuation for Weighted Nearest Neighbor Algorithms
Stochastic Extragradient with Random Reshuffling: Improved Convergence for Variational Inequalities
Learning Granger Causality from Instance-wise Self-attentive Hawkes Processes
DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data
Orthogonal Gradient Boosting for Simpler Additive Rule Ensembles
Towards Generalizable and Interpretable Motion Prediction: A Deep Variational Bayes Approach
On the Model-Misspecification in Reinforcement Learning
Learning Populations of Preferences via Pairwise Comparison Queries
SDMTR: A Brain-inspired Transformer for Relation Inference
Thompson Sampling Itself is Differentially Private
Sharpened Lazy Incremental Quasi-Newton Method
Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent in High-Dimensional Least Squares
Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks
Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation
Causally Inspired Regularization Enables Domain General Representations
Multi-Level Symbolic Regression: Function Structure Learning for Multi-Level Data
Learning Policies for Localized Interventions from Observational Data
Identification and Estimation of ``Causes of Effects'' using Covariate-Mediator Information
Proxy Methods for Domain Adaptation
Quantifying Uncertainty in Natural Language Explanations of Large Language Models
Unsupervised Change Point Detection in Multivariate Time Series
Density-Regression: Efficient and Distance-aware Deep Regressor for Uncertainty Estimation under Distribution Shifts
Trigonometric Quadrature Fourier Features for Scalable Gaussian Process Regression
Deep Dependency Networks and Advanced Inference Schemes for Multi-Label Classification
Fair Supervised Learning with A Simple Random Sampler of Sensitive Attributes
Stochastic Approximation with Delayed Updates: Finite-Time Rates under Markovian Sampling
Learning to Solve the Constrained Most Probable Explanation Task in Probabilistic Graphical Models
Integrating Uncertainty Awareness into Conformalized Quantile Regression
autoMALA: Locally adaptive Metropolis-adjusted Langevin algorithm
Consistency of Dictionary-Based Manifold Learning
Mixture-of-Linear-Experts for Long-term Time Series Forecasting
Multivariate Time Series Forecasting By Graph Attention Networks With Theoretical Guarantees
An Analytic Solution to Covariance Propagation in Neural Networks
Operationalizing Counterfactual Metrics: Incentives, Ranking, and Information Asymmetry
Coreset Markov chain Monte Carlo
End-to-end Feature Selection Approach for Learning Skinny Trees
Sample Efficient Learning of Factored Embeddings of Tensor Fields
Sequential Monte Carlo for Inclusive KL Minimization in Amortized Variational Inference
On the Effect of Key Factors in Spurious Correlation: A theoretical Perspective
Adaptive Compression in Federated Learning via Side Information
Robust Approximate Sampling via Stochastic Gradient Barker Dynamics
Fusing Individualized Treatment Rules Using Secondary Outcomes
Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
Cylindrical Thompson Sampling for High-Dimensional Bayesian Optimization
Enhancing In-context Learning via Linear Probe Calibration
Efficient Graph Laplacian Estimation by Proximal Newton
Learning Sparse Codes with Entropy-Based ELBOs
Uncertainty Matters: Stable Conclusions under Unstable Assessment of Fairness Results
Towards Achieving Sub-linear Regret and Hard Constraint Violation in Model-free RL
Faithful graphical representations of local independence
FairRR: Pre-Processing for Group Fairness through Randomized Response
THE SAMPLE COMPLEXITY OF ERM IN EUCLIDEAN STOCHASTIC CONVEX OPTIMIZATION
Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems
Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates
Compression with Exact Error Distribution for Federated Learning
Learning Latent Partial Matchings with Gumbel-IPF Networks
Discriminator Guidance for Autoregressive Diffusion Models
Meta Learning in Bandits within shared affine Subspaces
Asynchronous Randomized Trace Estimation
Posterior Uncertainty Quantification in Neural Networks using Data Augmentation
Backward Filtering Forward Deciding in Linear Non-Gaussian State Space Models
A Unifying Variational Framework for Gaussian Process Motion Planning
Multi-resolution Time-Series Transformer for Long-term Forecasting
Sample Complexity Characterization for Linear Contextual MDPs
Independent Learning in Constrained Markov Potential Games
BLIS-Net: Classifying and Analyzing Signals on Graphs
Gibbs-Based Information Criteria and the Over-Parameterized Regime
Certified private data release for sparse Lipschitz functions
Leveraging Ensemble Diversity for Robust Self-Training in the Presence of Sample Selection Bias
MIM-Reasoner: Learning with Theoretical Guarantees for Multiplex Influence Maximization
Informative Path Planning with Limited Adaptivity
Scalable Algorithms for Individual Preference Stable Clustering
Best Arm Identification with Resource Constraints
Variational Gaussian Process Diffusion Processes
Graph fission and cross-validation
Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games
Graph Pruning for Enumeration of Minimal Unsatisfiable Subsets
Manifold-Aligned Counterfactual Explanations for Neural Networks
Conditions on Preference Relations that Guarantee the Existence of Optimal Policies
Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors
Classifier Calibration with ROC-Regularized Isotonic Regression
Learning to Rank for Optimal Treatment Allocation Under Resource Constraints
Making Better Use of Unlabelled Data in Bayesian Active Learning
FALCON: FLOP-Aware Combinatorial Optimization for Neural Network Pruning
Functional Graphical Models: Structure Enables Offline Data-Driven Optimization
Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks
Efficiently Computable Safety Bounds for Gaussian Processes in Active Learning
Adaptive importance sampling for heavy-tailed distributions via $\alpha$-divergence minimization
Warped Diffusion for Latent Differentiation Inference
Federated Learning For Heterogeneous Electronic Health Records Utilising Augmented Temporal Graph Attention Networks
Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity
Variational Resampling
Think Global, Adapt Local: Learning Locally Adaptive K-Nearest Neighbor Kernel Density Estimators
Quantifying intrinsic causal contributions via structure preserving interventions
Fair Soft Clustering
Deep Classifier Mimicry without Data Access
Corruption-Robust Offline Two-Player Zero-Sum Markov Games
Multi-Agent Bandit Learning through Heterogeneous Action Erasure Channels
Random Oscillators Network for Time Series Processing
Transductive conformal inference with adaptive scores
Self-Compatibility: Evaluating Causal Discovery without Ground Truth
Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains
Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes
Membership Testing in Markov Equivalence Classes via Independence Queries
Risk Seeking Bayesian Optimization under Uncertainty for Obtaining Extremum
Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses
To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models
Online Distribution Learning with Local Privacy Constraints
Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization
Efficient Reinforcement Learning for Routing Jobs in Heterogeneous Queueing Systems
Privacy-Preserving Decentralized Actor-Critic for Cooperative Multi-Agent Reinforcement Learning
Bounding Box-based Multi-objective Bayesian Optimization of Risk Measures under Input Uncertainty
Data-Adaptive Probabilistic Likelihood Approximation for Ordinary Differential Equations
Causal Bandits with General Causal Models and Interventions
Density Uncertainty Layers for Reliable Uncertainty Estimation
Learning multivariate temporal point processes via the time-change theorem
Scalable Learning of Item Response Theory Models
Causal Modeling with Stationary Diffusions
Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence
Adaptive Experiment Design with Synthetic Controls
Nonparametric Automatic Differentiation Variational Inference with Spline Approximation
Monotone Operator Theory-Inspired Message Passing for Learning Long-Range Interaction on Graphs
Symmetric Equilibrium Learning of VAEs
Learning Sampling Policy to Achieve Fewer Queries for Zeroth-Order Optimization
Proving Linear Mode Connectivity of Neural Networks via Optimal Transport
The Effective Number of Shared Dimensions Between Paired Datasets
Learning Unknown Intervention Targets in Structural Causal Models from Heterogeneous Data
Analysis of Kernel Mirror Prox for Measure Optimization
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
Inconsistency of Cross-Validation for Structure Learning in Gaussian Graphical Models
On the Impact of Overparameterization on the Training of a Shallow Neural Network in High Dimensions
Stochastic Approximation with Biased MCMC for Expectation Maximization
SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratification
Consistent Optimal Transport with Empirical Conditional Measures
Online non-parametric likelihood-ratio estimation by Pearson-divergence functional minimization
Differentiable Rendering with Reparameterized Volume Sampling
Neural McKean Vlasov Processes: Distributional Dependence in Diffusion Models
Riemannian Laplace Approximation with the Fisher Metric
On the connection between Noise-Contrastive Estimation and Contrastive Divergence
Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers
Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Support
Simulation-Free Schrödinger Bridges via Score and Flow Matching
Approximate Bayesian Class-Conditional Models under Continuous Representation Shift
Robust Data Clustering with Outliers via Transformed Tensor Low-Rank Representation
Optimal Sparse Survival Trees
Probabilistic Calibration by Design for Neural Network Regression
Probabilistic Integral Circuits
Data-Driven Confidence Intervals with Optimal Rates for the Mean of Heavy-Tailed Distributions
Bayesian Semi-structured Subspace Inference
Learning Under Random Distributional Shifts
Minimizing Convex Functionals over Space of Probability Measures via KL Divergence Gradient Flow
DNNLasso: Scalable Graph Learning for Matrix-Variate Data
BlockBoost: Scalable and Efficient Blocking through Boosting
Information-theoretic Analysis of Bayesian Test Data Sensitivity
Tackling the XAI Disagreement Problem with Regional Explanations
LP-based Construction of DC Decompositions for Efficient Inference of Markov Random Fields
Multiclass Learning from Noisy Labels for Non-decomposable Performance Measures
Directional Optimism for Safe Linear Bandits
Uncertainty-aware Continuous Implicit Neural Representations for Remote Sensing Object Counting
BOBA: Byzantine-Robust Federated Learning with Label Skewness
Subsampling Error in Stochastic Gradient Langevin Diffusions
A Greedy Approximation for k-Determinantal Point Processes
Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networks
GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models
Bayesian Online Learning for Consensus Prediction
Optimal estimation of Gaussian (poly)trees
Non-vacuous Generalization Bounds for Adversarial Risk in Stochastic Neural Networks
SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization
Stochastic Multi-Armed Bandits with Strongly Reward-Dependent Delays
Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Betting
Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures
Learning to Defer to a Population: A Meta-Learning Approach
Estimating treatment effects from single-arm trials via latent-variable modeling
Restricted Isometry Property of Rank-One Measurements with Random Unit-Modulus Vectors
Minimax optimal density estimation using a shallow generative model with a one-dimensional latent variable
Lower-level Duality Based Reformulation and Majorization Minimization Algorithm for Hyperparameter Optimization
Causal Q-Aggregation for CATE Model Selection
Efficient Variational Sequential Information Control
Emergent specialization from participation dynamics and multi-learner retraining
Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?
Probabilistic Modeling for Sequences of Sets in Continuous-Time
Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classification
Confident Feature Ranking
A Doubly Robust Approach to Sparse Reinforcement Learning
Functional Flow Matching
Oracle-Efficient Pessimism: Offline Policy Optimization In Contextual Bandits
Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
Tensor-view Topological Graph Neural Network
Towards a Complete Benchmark on Video Moment Localization
How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability
Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components
Sketch In, Sketch Out: Accelerating both Learning and Inference for Structured Prediction with Kernels
Multitask Online Learning: Listen to the Neighborhood Buzz
Optimal Zero-Shot Detector for Multi-Armed Attacks
Interpretability Guarantees with Merlin-Arthur Classifiers
Provable local learning rule by expert aggregation for a Hawkes network
Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent
Error bounds for any regression model using Gaussian processes with gradient information
Model-Based Best Arm Identification for Decreasing Bandits
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
Reparameterized Variational Rejection Sampling
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
Multi-Resolution Active Learning of Fourier Neural Operators
Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems
Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients
Deep Learning-Based Alternative Route Computation
Estimation of partially known Gaussian graphical models with score-based structural priors
The effect of Leaky ReLUs on the training and generalization of overparameterized networks
No-Regret Algorithms for Safe Bayesian Optimization with Monotonicity Constraints
On Feynman–Kac training of partial Bayesian neural networks
Identifying Copeland Winners in Dueling Bandits with Indifferences
Adaptive Batch Sizes for Active Learning: A Probabilistic Numerics Approach
Looping in the Human: Collaborative and Explainable Bayesian Optimization
Approximate Control for Continuous-Time POMDPs
Optimal Budgeted Rejection Sampling for Generative Models
On the (In)feasibility of ML Backdoor Detection as an Hypothesis Testing Problem
Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization
On Ranking-based Tests of Independence
Intrinsic Gaussian Vector Fields on Manifolds
Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions
Boundary-Aware Uncertainty for Feature Attribution Explainers
Safe and Interpretable Estimation of Optimal Treatment Regimes
Online Learning of Decision Trees with Thompson Sampling
Robust Offline Reinforcement Learning with Heavy-Tailed Rewards
Surrogate Bayesian Networks for Approximating Evolutionary Games
On Parameter Estimation in Deviated Gaussian Mixture of Experts
Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts
Breaking isometric ties and introducing priors in Gromov-Wasserstein distances
Fast and Adversarial Robust Kernelized SDU Learning
Online multiple testing with e-values
An Improved Algorithm for Learning Drifting Discrete Distributions
Local Causal Discovery with Linear non-Gaussian Cyclic Models
User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates
A General Algorithm for Solving Rank-one Matrix Sensing
Fast Dynamic Sampling for Determinantal Point Processes
Unsupervised Novelty Detection in Pretrained Representation Space with Locally Adapted Likelihood Ratio
Recovery Guarantees for Distributed-OMP
Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems
How Good is a Single Basin?
An Online Bootstrap for Time Series
Optimal Exploration is no harder than Thompson Sampling
Sinkhorn Flow as Mirror Flow: A Continuous-Time Framework for Generalizing the Sinkhorn Algorithm
Simple and scalable algorithms for cluster-aware precision medicine
Distributionally Robust Model-based Reinforcement Learning with Large State Spaces
Formal Verification of Unknown Stochastic Systems via Non-parametric Estimation
Length independent PAC-Bayes bounds for Simple RNNs
Vector Quantile Regression on Manifolds
MINTY: Rule-based models that minimize the need for imputing features with missing values
CAD-DA: Controllable Anomaly Detection after Domain Adaptation by Statistical Inference
GmGM: a fast multi-axis Gaussian graphical model
Adaptivity of Diffusion Models to Manifold Structures
From Data Imputation to Data Cleaning --- Automated Cleaning of Tabular Data Improves Downstream Predictive Performance
On-Demand Federated Learning for Arbitrary Target Class Distributions
Soft-constrained Schr\"odinger Bridge: a Stochastic Control Approach
Don't Be Pessimistic Too Early: Look K Steps Ahead!
Supervised Feature Selection via Ensemble Gradient Information from Sparse Neural Networks
Training Implicit Generative Models via an Invariant Statistical Loss
A Neural Architecture Predictor based on GNN-Enhanced Transformer
Dissimilarity Bandits
Computing epidemic metrics with edge differential privacy
A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization
Comparing Comparators in Generalization Bounds
RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model
A Scalable Algorithm for Individually Fair k-Means Clustering
Hodge-Compositional Edge Gaussian Processes
Diagonalisation SGD: Fast \& Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean
Conformalized Semi-supervised Random Forest for Classification and Abnormality Detection
Private Learning with Public Features
First Passage Percolation with Queried Hints
Online learning in bandits with predicted context
Fair Machine Unlearning: Data Removal while Mitigating Disparities
Adaptive Federated Minimax Optimization with Lower Complexities
Stochastic Frank-Wolfe: Unified Analysis and Zoo of Special Cases
Weight-Sharing Regularization
Taming False Positives in Out-of-Distribution Detection with Human Feedback
Consistent Hierarchical Classification with A Generalized Metric
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization
Learning Adaptive Kernels for Statistical Independence Tests
Faster Recalibration of an Online Predictor via Approachability
Large-Scale Gaussian Processes via Alternating Projection
Sum-max Submodular Bandits
LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detection
Solving General Noisy Inverse Problem via Posterior Sampling: A Policy Gradient Viewpoint
Simulation-Based Stacking
Reward-Relevance-Filtered Linear Offline Reinforcement Learning
Queuing dynamics of asynchronous Federated Learning
Delegating Data Collection in Decentralized Machine Learning
On the Nystr\"om Approximation for Preconditioning in Kernel Machines
Understanding the Generalization Benefits of Late Learning Rate Decay
On learning history-based policies for controlling Markov decision processes
Submodular Minimax Optimization: Finding Effective Sets
Score Operator Newton transport
Adaptive and non-adaptive minimax rates for weighted Laplacian-Eigenmap based nonparametric regression
Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees
DE-HNN: An effective neural model for Circuit Netlist representation
Resilient Constrained Reinforcement Learning
Constant or Logarithmic Regret in Asynchronous Multiplayer Bandits with Limited Communication
Differentially Private Conditional Independence Testing
A General Theoretical Paradigm to Understand Learning from Human Preferences
Continual Domain Adversarial Adaptation via Double-Head Discriminators
A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent
Differentially Private Reward Estimation with Preference Feedback
On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation
Explanation-based Training with Differentiable Insertion/Deletion Metric-aware Regularizers
Smoothness-Adaptive Dynamic Pricing with Nonparametric Demand Learning
Solving Attention Kernel Regression Problem via Pre-conditioner
Efficient Quantum Agnostic Improper Learning of Decision Trees
Conformal Contextual Robust Optimization
Robust SVD Made Easy: A fast and reliable algorithm for large-scale data analysis
XB-MAML: Learning Expandable Basis Parameters for Effective Meta-Learning with Wide Task Coverage
Fixed-Budget Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
SDEs for Minimax Optimization
Multi-objective Optimization via Wasserstein-Fisher-Rao Gradient Flow
Contextual Bandits with Budgeted Information Reveal
Filter, Rank, and Prune: Learning Linear Cyclic Gaussian Graphical Models
On the Privacy of Selection Mechanisms with Gaussian Noise
The Solution Path of SLOPE
Analysis of Using Sigmoid Loss for Contrastive Learning
TenGAN: Pure Transformer Encoders Make an Efficient Discrete GAN for De Novo Molecular Generation
Testing exchangeability by pairwise betting
On the Generalization Ability of Unsupervised Pretraining
Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
Optimal Transport for Measures with Noisy Tree Metric
Theory-guided Message Passing Neural Network for Probabilistic Inference
Efficient Conformal Prediction under Data Heterogeneity
A White-Box False Positive Adversarial Attack Method on Contrastive Loss Based Offline Handwritten Signature Verification Models
Federated Linear Contextual Bandits with Heterogeneous Clients
FedFisher: Leveraging Fisher Information for One-Shot Federated Learning
VEC-SBM: Optimal Community Detection with Vectorial Edges Covariates
Causal Discovery under Off-Target Interventions
Efficient Neural Architecture Design via Capturing Architecture-Performance Joint Distribution
Provable Policy Gradient Methods for Average-Reward Markov Potential Games
Robust Non-linear Normalization of Heterogeneous Feature Distributions with Adaptive Tanh-Estimators
Testing Generated Distributions in GANs to Penalize Mode Collapse
Learning Cartesian Product Graphs with Laplacian Constraints
Adaptive Discretization for Event PredicTion (ADEPT)
Fast Fourier Bayesian Quadrature
HintMiner: Automatic Question Hints Mining From Q\&A Web Posts with Language Model via Self-Supervised Learning
A 4-Approximation Algorithm for Min Max Correlation Clustering
Acceleration and Implicit Regularization in Gaussian Phase Retrieval
Robust variance-regularized risk minimization with concomitant scaling
Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits \& Dueling Bandits
Auditing Fairness under Unobserved Confounding
Cross-model Mutual Learning for Exemplar-based Medical Image Segmentation
Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimation
Conditional Adjustment in a Markov Equivalence Class
Analysis of Privacy Leakage in Federated Large Language Models
Maximum entropy GFlowNets with soft Q-learning
A Cubic-regularized Policy Newton Algorithm for Reinforcement Learning
The Relative Gaussian Mechanism and its Application to Private Gradient Descent
Personalized Federated X-armed Bandit
Multi-Agent Learning in Contextual Games under Unknown Constraints
Multi-Dimensional Hyena for Spatial Inductive Bias
Accuracy-Preserving Calibration via Statistical Modeling on Probability Simplex
Central Limit Theorem for Two-Timescale Stochastic Approximation with Markovian Noise: Theory and Applications
ALAS: Active Learning for Autoconversion Rates Prediction from Satellite Data
Ordinal Potential-based Player Rating
Autoregressive Bandits
AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms
A Specialized Semismooth Newton Method for Kernel-Based Optimal Transport
Anytime-Constrained Reinforcement Learning
Contextual Directed Acyclic Graphs
Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation
Proximal Causal Inference for Synthetic Control with Surrogates
Fast 1-Wasserstein distance approximations using greedy strategies
Scalable Higher-Order Tensor Product Spline Models
Fair k-center Clustering with Outliers
Offline Primal-Dual Reinforcement Learning for Linear MDPs
On Convergence in Wasserstein Distance and f-divergence Minimization Problems
Regret Bounds for Risk-sensitive Reinforcement Learning with Lipschitz Dynamic Risk Measures
Learning Dynamics in Linear VAE: Posterior Collapse Threshold, Superfluous Latent Space Pitfalls, and Speedup with KL Annealing
A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity
Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective
Distributionally Robust Quickest Change Detection using Wasserstein Uncertainty Sets
Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability
Equivalence Testing: The Power of Bounded Adaptivity
Learning Fair Division from Bandit Feedback
Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo
Pr{I}sing: Privacy-Preserving Peer Effect Estimation via {I}sing Model
Better Batch for Deep Probabilistic Time Series Forecasting
Mixed variational flows for discrete variables
General Identifiability and Achievability for Causal Representation Learning
Sparse and Faithful Explanations Without Sparse Models
Identifying Confounding from Causal Mechanism Shifts
Mitigating Underfitting in Learning to Defer with Consistent Losses
Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach
Understanding Inverse Scaling and Emergence in Multitask Representation Learning
Benchmarking Observational Studies with Experimental Data under Right-Censoring
SADI: Similarity-Aware Diffusion Model-Based Imputation for Incomplete Temporal EHR Data
Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements
Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection
Fast and Accurate Estimation of Low-Rank Matrices from Noisy Measurements via Preconditioned Non-Convex Gradient Descent
Interpretable Causal Inference for Analyzing Wearable, Sensor, and Distributional Data
Achieving Group Distributional Robustness and Minimax Group Fairness with Interpolating Classifiers
Bandit Pareto Set Identification: the Fixed Budget Setting
Can Probabilistic Feedback Drive User Impacts in Online Platforms?
Lexicographic Optimization: Algorithms and Stability
Federated Experiment Design under Distributed Differential Privacy
An Impossibility Theorem for Node Embedding
Equation Discovery with Bayesian Spike-and-Slab Priors and Efficient Kernels
Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data
Online Learning in Contextual Second-Price Pay-Per-Click Auctions
Learning Safety Constraints from Demonstrations with Unknown Rewards
Approximate Leave-one-out Cross Validation for Regression with l1 Regularizers
Simulating weighted automata over sequences and trees with transformers
Implicit Regularization in Deep Tucker Factorization: Low-Rankness via Structured Sparsity
EM for Mixture of Linear Regression with Clustered Data
An Efficient Stochastic Algorithm for Decentralized Nonconvex-Strongly-Concave Minimax Optimization
Ethics in Action: Training Reinforcement Learning Agents for Moral Decision-making In Text-based Adventure Games
Positivity-free Policy Learning with Observational Data
Time to Cite: Modeling Citation Networks using the Dynamic Impact Single-Event Embedding Model
Bures-Wasserstein Means of Graphs
DAGnosis: Localized Identification of Data Inconsistencies using Structures
Structural perspective on constraint-based learning of Markov networks
Conformalized Deep Splines for Optimal and Efficient Prediction Sets
Feasible $Q$-Learning for Average Reward Reinforcement Learning
Offline Policy Evaluation and Optimization Under Confounding
Online Calibrated and Conformal Prediction Improves Bayesian Optimization
Sequence Length Independent Norm-Based Generalization Bounds for Transformers
Generalization Bounds for Label Noise Stochastic Gradient Descent
Gaussian process regression with Sliced Wasserstein Weisfeiler-Lehman graph kernels
Quantized Fourier and Polynomial Features for more Expressive Tensor Network Models
When No-Rejection Learning is Consistent for Regression with Rejection
Unified Transfer Learning in High-Dimensional Linear Regression
Efficient Low-Dimensional Compression of Overparameterized Models
Robust Sparse Voting
Graph Machine Learning through the Lens of Bilevel Optimization
Learning-Based Algorithms for Graph Searching Problems
Monitoring machine learning-based risk prediction algorithms in the presence of performativity
Adaptive Quasi-Newton and Anderson Acceleration Framework with Explicit Global (Accelerated) Convergence Rates
Sharp error bounds for imbalanced classification: how many examples in the minority class?
Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers
A Unified Framework for Discovering Discrete Symmetries
E(3)-Equivariant Mesh Neural Networks
Exploration via linearly perturbed loss minimisation
Understanding Generalization of Federated Learning via Stability: Heterogeneity Matters
Deep anytime-valid hypothesis testing
Clustering Items From Adaptively Collected Inconsistent Feedback
Structured Transforms Across Spaces with Cost-Regularized Optimal Transport
Graph Partitioning with a Move Budget
The Risks of Recourse in Binary Classification
The Galerkin method beats Graph-Based Approaches for Spectral Algorithms
Faster Convergence with MultiWay Preferences
Multi-armed bandits with guaranteed revenue per arm
Pure Exploration in Bandits with Linear Constraints
A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning
Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
Agnostic Multi-Robust Learning using ERM
Optimising Distributions with Natural Gradient Surrogates
Free-form Flows: Make Any Architecture a Normalizing Flow
Understanding Progressive Training Through the Framework of Randomized Coordinate Descent
Enhancing Distributional Stability among Sub-populations
Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses
Extragradient Type Methods for Riemannian Variational Inequality Problems
Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources
Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
On the Vulnerability of Fairness Constrained Learning to Malicious Noise
Pessimistic Off-Policy Multi-Objective Optimization
Near-optimal Per-Action Regret Bounds for Sleeping Bandits
Is this model reliable for everyone? Testing for strong calibration
Double InfoGAN for Contrastive Analysis
Mind the GAP: Improving Robustness to Subpopulation Shifts with Group-Aware Priors
Asynchronous SGD on Graphs: a Unified Framework for Asynchronous Decentralized and Federated Optimization
Achieving Fairness through Separability: A Unified Framework for Fair Representation Learning
A/B testing under Interference with Partial Network Information
Sequential learning of the Pareto front for multi-objective bandits
Why is parameter averaging beneficial in SGD? An objective smoothing perspective
On the price of exact truthfulness in incentive-compatible online learning with bandit feedback: a regret lower bound for WSU-UX
Information Theoretically Optimal Sample Complexity of Learning Dynamical Directed Acyclic Graphs
Complexity of Single Loop Algorithms for Nonlinear Programming with Stochastic Objective and Constraints
Model-based Policy Optimization under Approximate Bayesian Inference
NoisyMix: Boosting Model Robustness to Common Corruptions
Non-Convex Joint Community Detection and Group Synchronization via Generalized Power Method
Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate
Identifiability of Product of Experts Models
Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
Fast Minimization of Expected Logarithmic Loss via Stochastic Dual Averaging
Mechanics of Next Token Prediction with Self-Attention
Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games
Convergence to Nash Equilibrium and No-regret Guarantee in (Markov) Potential Games
Joint control variate for faster black-box variational inference
Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning
Surrogate Active Subspaces for Jump-Discontinuous Functions
Towards Costless Model Selection in Contextual Bandits: A Bias-Variance Perspective
Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention
On the Misspecification of Linear Assumptions in Synthetic Controls
Invariant Aggregator for Defending against Federated Backdoor Attacks
Low-rank MDPs with Continuous Action Spaces
Decentralized Multi-Level Compositional Optimization Algorithms with Level-Independent Convergence Rate
Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression
Categorical Generative Model Evaluation via Synthetic Distribution Coarsening
Any-dimensional equivariant neural networks
Identifiable Feature Learning for Spatial Data with Nonlinear ICA
Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization
Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis
Equivariant bootstrapping for uncertainty quantification in imaging inverse problems
We use cookies to store which papers have been visited.
I agree
Successful Page Load
AISTATS uses cookies to remember that you are logged in. By using our websites, you agree to the placement of cookies.
Our Privacy Policy »
Accept Cookies